Jointly Learning Knowledge Embedding and Neighborhood Consensus with Relational Knowledge Distillation for Entity Alignment

TL;DR

This paper introduces RKDEA, a GCN-based model that jointly learns entity embeddings and neighborhood consensus for entity alignment by leveraging relational knowledge distillation to effectively incorporate relation semantics.

Contribution

The paper proposes a novel GCN-based framework with adaptive relational knowledge distillation to improve entity alignment by jointly learning embeddings and neighborhood consensus.

Findings

RKDEA outperforms existing methods on benchmark datasets.

Relational knowledge distillation enhances relation semantic integration.

Joint learning improves entity alignment accuracy.

Abstract

Entity alignment aims at integrating heterogeneous knowledge from different knowledge graphs. Recent studies employ embedding-based methods by first learning the representation of Knowledge Graphs and then performing entity alignment via measuring the similarity between entity embeddings. However, they failed to make good use of the relation semantic information due to the trade-off problem caused by the different objectives of learning knowledge embedding and neighborhood consensus. To address this problem, we propose Relational Knowledge Distillation for Entity Alignment (RKDEA), a Graph Convolutional Network (GCN) based model equipped with knowledge distillation for entity alignment. We adopt GCN-based models to learn the representation of entities by considering the graph structure and incorporating the relation semantic information into GCN via knowledge distillation. Then, we introduce a novel adaptive mechanism to transfer relational knowledge so as to jointly learn entity embedding and neighborhood consensus. Experimental results on several benchmarking datasets demonstrate the effectiveness of our proposed model.